Robust Fairness

Robust fairness in machine learning aims to develop models that are both accurate and fair, even when faced with adversarial attacks or distributional shifts. Current research focuses on adversarial training techniques, often incorporating modifications like weighted losses or curvature matching to address disparities in model performance across different groups or under various input perturbations. This work is crucial for building trustworthy AI systems, mitigating biases that disproportionately affect certain populations, and ensuring reliable performance in real-world scenarios where data is noisy or subject to manipulation. The ultimate goal is to create models that are not only accurate on average but also consistently fair across all subgroups and robust to various forms of uncertainty.

Papers

October 10, 2024

No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
Mengxuan Hu, Hongyi Wu, Zihan Guan, Ronghang Zhu, Dongliang Guo, Daiqing Qi, Sheng Li
Large Language Model Retrieval Augmented Generation Free Lunch Fairness Implication Robust Fairness

April 1, 2024

The Double-Edged Sword of Input Perturbations to Robust Accurate Fairness
Xuran Li, Peng Wu, Yanting Chen, Xingjun Ma, Zhen Zhang, Kaixiang Dong
Adversarial Perturbation Input Perturbation Adversarial Instance Robust Fairness Adversarial Bias

February 27, 2024

Towards Fairness-Aware Adversarial Learning
Yanghao Zhang, Tianle Zhang, Ronghui Mu, Xiaowei Huang, Wenjie Ruan
Adversarial Training Distributionally Robust Optimization Fair Adversarial Robust Fairness

January 23, 2024

DAFA: Distance-Aware Fair Adversarial Training
Hyungyu Lee, Saehyung Lee, Hyemi Jang, Junsung Park, Ho Bae, Sungroh Yoon
Adversarial Attack Adversarial Training Fair Adversarial Robust Fairness Adversarial Change

November 15, 2023

Beyond Detection: Unveiling Fairness Vulnerabilities in Abusive Language Models
Yueqing Liang, Lu Cheng, Ali Payani, Kai Shu
Data Detection Backdoor Attack Abusive Language Detection Effective Model Fair Adversarial Robust Fairness Unveiling Vulnerability Abusive Language Classifier

September 20, 2023

Dr. FERMI: A Stochastic Distributionally Robust Fair Empirical Risk Minimization Framework
Sina Baharlouei, Meisam Razaviyayn
Empirical Risk Minimization Fair Machine Learning Robust Fairness Fair Inference

August 3, 2023

Hard Adversarial Example Mining for Improving Robust Fairness
Chenhao Lin, Xiang Ji, Yulong Yang, Qian Li, Chao Shen, Run Wang, Liming Fang
Adversarial Example Adversarial Training Adversarial Instance Robust Fairness

September 22, 2022

Fair Robust Active Learning by Joint Inconsistency
Tsung-Han Wu, Hung-Ting Su, Shang-Tse Chen, Winston H. Hsu
Native Robustness Demographic Fairness Robust Fairness Joint Action

September 15, 2022

Improving Robust Fairness via Balance Adversarial Training
Chunyu Sun, Chenye Xu, Chengyuan Yao, Siyuan Liang, Yichao Wu, Ding Liang, XiangLong Liu, Aishan Liu
Adversarial Example Adversarial Training Robust Fairness Class Fairness

July 4, 2022

How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts
Haotao Wang, Junyuan Hong, Jiayu Zhou, Zhangyang Wang
Neural Network Procedural Fairness Distribution Shift Fairness Aware Machine Fairness Datasets Robust Fairness

May 18, 2022

Accurate Fairness: Improving Individual Fairness without Trading Accuracy
Xuran Li, Peng Wu, Jing Su
AI Fairness Individual Fairness Robust Fairness